diff options
| author | Iwan Kawrakow <iwan.kawrakow@gmail.com> | 2024-06-17 18:41:30 +0300 |
|---|---|---|
| committer | Iwan Kawrakow <iwan.kawrakow@gmail.com> | 2024-06-22 12:02:51 +0300 |
| commit | f6863cfa1bbc5ac42b78837b355e45d82246a472 (patch) | |
| tree | b4718a3e7f7796f2bd5f8f4e6f81a812eeadae32 /ggml-quants.c | |
| parent | 765622ff8f921319f6b30c556b378d8320500c95 (diff) | |
bitnet: add 2 bpw quantization
The scalar dot product already chieves 37 t/s for TG!
Diffstat (limited to 'ggml-quants.c')
| -rw-r--r-- | ggml-quants.c | 1 |
1 files changed, 1 insertions, 0 deletions
diff --git a/ggml-quants.c b/ggml-quants.c index 31817b1c..f1ce1345 100644 --- a/ggml-quants.c +++ b/ggml-quants.c @@ -15056,6 +15056,7 @@ bool ggml_validate_row_data(enum ggml_type type, const void * data, size_t nbyte case GGML_TYPE_I32: case GGML_TYPE_I64: case GGML_TYPE_IQ1_BN: + case GGML_TYPE_IQ2_BN: // nothing to validate break; default: |